From 4402d5701b04b7c848f726d1fbe6e6e3c0001e2f Mon Sep 17 00:00:00 2001 From: HuiLi <1324982600@qq.com> Date: Sat, 15 Jun 2024 08:10:23 +0000 Subject: [PATCH] docs & fix: update docs and modify requirements --- README.md | 12 ++++++------ requirements.txt | 1 + 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 198234dd..45cf30a4 100644 --- a/README.md +++ b/README.md @@ -63,6 +63,11 @@ Install packages with `pip` pip install . ``` +Besides, ffmpeg is also need: +```bash + apt-get install ffmpeg +``` + # Inference The inference entrypoint script is `scripts/inference.py`. Before testing your cases, there are two preparations need to be completed: @@ -110,7 +115,6 @@ Finally, these pretrained models should be organized as follows: | `-- mm_sd_v15_v2.ckpt |-- sd-vae-ft-mse/ | |-- config.json -| |-- diffusion_pytorch_model.bin | `-- diffusion_pytorch_model.safetensors |-- stable-diffusion-v1-5/ | |-- feature_extractor/ @@ -118,7 +122,7 @@ Finally, these pretrained models should be organized as follows: | |-- model_index.json | |-- unet/ | | |-- config.json -| | `-- diffusion_pytorch_model.bin +| | `-- diffusion_pytorch_model.safetensors | `-- v1-inference.yaml `-- wav2vec/ |-- wav2vec2-base-960h/ @@ -126,13 +130,9 @@ Finally, these pretrained models should be organized as follows: | |-- feature_extractor_config.json | |-- model.safetensors | |-- preprocessor_config.json - | |-- pytorch_model.bin | |-- special_tokens_map.json - | |-- tf_model.h5 | |-- tokenizer_config.json | `-- vocab.json - `-- wav2vec2-large-960h/ - `-- ... ``` ## Run inference diff --git a/requirements.txt b/requirements.txt index 063e4a68..40eff183 100644 --- a/requirements.txt +++ b/requirements.txt @@ -14,6 +14,7 @@ numpy==1.26.4 omegaconf==2.3.0 onnx2torch==1.5.14 onnx==1.16.1 +onnxruntime==1.18.0 opencv-contrib-python==4.9.0.80 opencv-python-headless==4.9.0.80 opencv-python==4.9.0.80